Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking

arXiv:2605.00348v1 Announce Type: cross Abstract: Recent multi-bit watermarking methods for large language models (LLMs) prioritize capacity over reliability, often conflating decoding with detection. Our analysis reveals that existing ECC-based extractors suffer from catastrophic false positive rates (FPR), and applying rejection thresholds merely collapses detection sensitivity (TPR) to random guessing. To resolve this structural limitation, we propose extbf{BREW} (Block-wise Reliable Embedding for Watermarking), a framework shifting the paradigm to designated verification. BREW employs a two-stage mechanism: (i) extbf{blind message estimation} via independent block voting, followed by (ii) extbf{window-shifting verification} that rigorously validates the payload against local edits. Experiments demonstrate that BREW achieves a TPR of 0.965 with an FPR of 0.02 under 10% synonym substitution, demonstrating that the high-FPR issue is not an inherent trade-off of multi-bit watermarking, but a solvable structural flaw of prior decoding-centric designs. Our framework is model-agnostic and theoretically grounded, providing a scalable solution for reliable forensic deployment.

Source: arXiv cs.CL | 2026-05-04